Merge pull request #1 from LCTT/master

更新

changelog.md

@@ -1,5 +1,9 @@
 # 变更日志
 
+## 0.0.23
+
+1. **紧急修复** 加入公共域的显示以及过滤 github 的邮箱 。 Contributor: @wxy
+
 ## 0.0.22
 
 1. **新特性** 不统计 Fork 来的仓库

github_org_china.md

@@ -0,0 +1,42 @@
+### 国内公司开源项目 GitHub 地址
+
+- [阿里巴巴](https://github.com/alibaba) 
+  - [Ant Design](https://github.com/ant-design) 
+  - [蚂蚁金服](https://github.com/antvis)
+  - [Angular Developers](https://github.com/NG-ZORRO) 
+  - [支付宝](https://github.com/aliceui) 
+  - [kissyteam](https://github.com/kissyteam)
+  - [淘宝](https://github.com/taobao)
+  - [天猫](https://github.com/tmallfe)
+  - [seajs](https://github.com/seajs)
+  - [eggjs](https://github.com/eggjs)
+- [华为](https://github.com/Huawei) 
+  - [华为 Hadoop](https://github.com/Huawei-Hadoop)  
+- [腾讯](https://github.com/tencent) 
+  - [AlloyTeam](https://github.com/AlloyTeam) 
+- [百度](https://github.com/baidu) 
+  - [FEX](https://github.com/fex-team)  
+  - [EFE](https://github.com/ecomfe)  
+  - [前端](https://github.com/be-fe)  
+- [饿了么](https://github.com/eleme)  
+  - [前端](https://github.com/elemefe) 
+- [网易](https://github.com/netease) 
+- [搜狐](https://github.com/SOHUDBA) 
+- [奇虎360](https://github.com/Qihoo360)  
+  - [360企业安全](https://github.com/360EntSecGroup-Skylar)  
+- [唯品会](https://github.com/vipshop)  
+- [豆瓣](https://github.com/douban) 
+- [大众点评](https://github.com/dianping) 
+- [美团点评](https://github.com/Meituan-Dianping)  
+- [小米](https://github.com/xiaomi) 
+- [美团](https://github.com/meituan) 
+- [蘑菇街](https://github.com/mogujie) 
+- [豌豆荚](https://github.com/CodisLabs) 
+- [当当](https://github.com/dangdangdotcom)  
+- [有赞](https://github.com/youzan)  
+- [深度](https://github.com/linuxdeepin) 
+- [DNSPod](https://github.com/DNSPod) 
+- [新浪微博](https://github.com/weibocom) 
+
+（最初参考[来源](https://github.com/jaywcjlove/handbook/blob/master/other/Github-Oraganizations.md)，去除了文档类项目。）
+

grank/script/crawler.py

@@ -15,6 +15,8 @@ def fetch_repo_data(owner, repository, config):
     # 添加一个可过滤掉的数据，确保后续执行完成
     commitArray.append({
         'author': 'localhost',
+        'domain': '',
+        'is_corp': False,
         'date': '未标注时间',
         "times": 1
     })

grank/script/social.py

@@ -24,11 +24,11 @@ def analyse_email(data,config):
     df = pd.DataFrame(data["commitArray"])
 
     for index,row in df.iterrows():
-        df.loc[index,"author"] = helpers.detect_email_dmain(row["author"])
+        df.loc[index,"domain"] = helpers.detect_email_domain(row["author"])
 
     click.echo('')
     # click.echo(df['author'].value_counts().drop(labels=common_mail,errors='ignore'))
-    click.echo(df['author'].value_counts().drop(labels=ignore_mail,errors='ignore'))
+    click.echo(df['domain'].value_counts().drop(labels=ignore_mail,errors='ignore'))
     click.echo('')
 
     new_rule = click.prompt('请输入新的社区化识别的正则规则',default=config["social"]["rule"])
@@ -52,13 +52,16 @@ def analyse_repo(owner, repository, data, config):
         np.zeros((len(date_range),), dtype=int), index=date_range)
 
     social_all_frame = pd.DataFrame(commitArray)
-    social_all_frame = social_all_frame[(social_all_frame.author != '') & (social_all_frame.author != '@users.noreply.github.com') & (social_all_frame.date != "未标注时间")]
+    for index,row in social_all_frame.iterrows():
+        social_all_frame.loc[index,"domain"] = helpers.detect_email_domain(row["author"])
+
+    social_all_frame = social_all_frame[(social_all_frame.domain != '') & (social_all_frame.domain != '@users.noreply.github.com') & (social_all_frame.date != "未标注时间")]
     social_all_frame["date"] = pd.to_datetime(social_all_frame['date'])
     for index, row in social_all_frame.iterrows():
-        social_all_frame.loc[index, "author"] = helpers.is_corp(
-            row["author"], config)
+        social_all_frame.loc[index, "is_corp"] = helpers.is_corp(
+            row["domain"], config)
 
-    community_df = social_all_frame[social_all_frame.author != True].set_index(
+    community_df = social_all_frame[social_all_frame.is_corp != True].set_index(
         'date').resample('W')['times'].sum()
     social_all_df = social_all_frame.set_index(
         'date').resample('W')['times'].sum()

requirements.txt

@@ -1,22 +1,22 @@
-bleach==2.1.4
+atomicwrites==1.2.1
+attrs==18.2.0
 certifi==2018.8.24
-cffi==1.11.5
 chardet==3.0.4
 Click==7.0
-cmarkgfm==0.4.2
-docopt==0.6.2
-docutils==0.14
-future==0.16.0
-html5lib==1.0.1
+cycler==0.10.0
+Grank==0.0.23
 idna==2.7
-pkginfo==1.4.2
-pycparser==2.19
-Pygments==2.2.0
-readme-renderer==22.0
+kiwisolver==1.0.1
+matplotlib==3.0.0
+more-itertools==4.3.0
+numpy==1.15.2
+pandas==0.23.4
+pluggy==0.7.1
+py==1.6.0
+pyparsing==2.2.2
+pytest==3.8.2
+python-dateutil==2.7.3
+pytz==2018.5
 requests==2.19.1
-requests-toolbelt==0.8.0
 six==1.11.0
-tqdm==4.26.0
-twine==1.12.1
-urllib3==1.23
-webencodings==0.5.1
+urllib3==1.23

setup.py

@@ -2,9 +2,10 @@
 
 setuptools.setup(
     name="Grank",
-    version="0.0.22",
+    version="0.0.23",
     author="Bestony@LCTT",
     author_email="[email protected]",
+    python_requires=">=3.4",
     description="A Github Project Rank Command Line Tool",
     long_description=open('README.rst').read(),
     url="https://github.com/LCTT/Grank",

tests/__init__.py

@@ -0,0 +1,4 @@
+def setup():
+    import warnings
+    warnings.resetwarnings()
+    warnings.simplefilter("always")

tests/test_helpers.py

@@ -0,0 +1,14 @@
+import pandas
+from grank.libs import helpers
+def test_detect_email_dmain():
+    gmail_domain = helpers.detect_email_dmain('[email protected]')
+    assert gmail_domain == '@gmail.com'
+
+    localhost_domain = helpers.detect_email_dmain('localhost')
+    assert localhost_domain == ''
+
+def test_get_user_type():
+    test_user = helpers.get_user_type('bestony')
+    assert test_user == True
+    test_ogran = helpers.get_user_type('lctt')
+    assert test_ogran == False